Indian Institute of Technology Kanpur

Selected work

Representative Papers

Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy

Feb 06, 2026

This study addresses the challenge of automatically identifying singing errors in music education by proposing the first teaching-oriented singing error detection framework. Leveraging synchronously recorded audio from both teachers and students, the authors construct a dedicated dataset with a fine-grained error annotation scheme and develop a deep learning model for error recognition. Experimental results demonstrate that the proposed method significantly outperforms traditional rule-based baselines. A systematic analysis further reveals the impact of inter-teacher instructional variability on error detection performance. This work contributes a novel benchmark dataset, an evaluation methodology, and actionable pedagogical insights for intelligent music education systems.

3 citationsRead paper

A Novel Approach to Tomato Harvesting Using a Hybrid Gripper with Semantic Segmentation and Keypoint Detection

Dec 21, 2024arXiv.org

Tomato harvesting faces challenges of fruit fragility and complex, dynamic environments, leading to poor recognition robustness and low grasping safety. Method: This paper proposes an autonomous harvesting approach integrating multimodal RGB-D vision perception with a bioinspired hybrid gripper. A semantic segmentation and keypoint detection framework enables precise localization of mature tomatoes under occlusion and varying illumination. The gripper combines a rigid exoskeleton with a flexible negative Poisson’s ratio structure, enabling adjustable grasping force and soft enveloping capability. Scotch-Yoke servo actuation and real-time trajectory planning ensure gentle, stable manipulation. Contribution/Results: Experiments demonstrate 96.2% recognition accuracy across ripeness stages and a 91.7% harvesting success rate—significantly outperforming conventional grippers—establishing a new paradigm for high-precision, low-damage agricultural robotics.

2 citationsRead paper

Rudraksh: A compact and lightweight post-quantum key-encapsulation mechanism

Jan 23, 2025IACR Cryptology ePrint Archive

To address quantum threats against resource-constrained IoT devices, this paper proposes a lightweight lattice-based key encapsulation mechanism (LWE-KEM). Methodologically, it introduces the first systematic optimization of LWE parameters—including polynomial dimension, modulus structure, modular reduction algorithms, and error distribution—tailored for hardware efficiency. It innovatively substitutes ASCON for Keccak in PRNG and hash functionalities, significantly improving cryptographic primitive performance. Furthermore, it integrates a CCA-secure construction with joint area–timing optimization targeting FPGA implementations. Experimental results demonstrate that, at NIST Level I security (≥AES-128), the proposed design reduces FPGA logic area by approximately 3× compared to the most compact Kyber implementation, achieves a 63%–76% higher operating frequency, and improves the time–area product by 2×—yielding substantial gains in hardware energy efficiency.

1 citationsRead paper